DAS-PINNs uses normalizing flows to adaptively sample collocation points based on PDE residuals in unified spacetime domains for high-dimensional time-dependent PDEs.
Moving sample method for solving time- dependent partial differential equations.arXiv preprint arXiv:2601.18575, 2026
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.NA 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
PMSM and WR-PMSM adaptively transport collocation samples according to residual dynamics in a progressive time-stepping scheme, outperforming standard PINNs and prior MSM on four benchmarks under matched budgets.
citing papers explorer
-
DAS-PINNs for high-dimensional partial differential equations: extending deep adaptive sampling to spacetime domains
DAS-PINNs uses normalizing flows to adaptively sample collocation points based on PDE residuals in unified spacetime domains for high-dimensional time-dependent PDEs.
-
Predictive Moving Sample Method for Physics-Informed Neural Solvers of Time-Dependent PDEs
PMSM and WR-PMSM adaptively transport collocation samples according to residual dynamics in a progressive time-stepping scheme, outperforming standard PINNs and prior MSM on four benchmarks under matched budgets.